US 12,277,699 B2
Method for determining quality of inspection data using machine learning model, information processing apparatus, and non-transitory computer readable storage medium storing computer program
Hikaru Kurasawa, Matsumoto (JP)
Assigned to SEIKO EPSON CORPORATION, Tokyo (JP)
Filed by SEIKO EPSON CORPORATION, Tokyo (JP)
Filed on Jun. 29, 2022, as Appl. No. 17/809,749.
Prior Publication US 2023/0005119 A1, Jan. 5, 2023
Int. Cl. G06T 7/00 (2017.01); G06V 10/74 (2022.01); G06V 10/764 (2022.01); G06V 10/776 (2022.01); G06V 10/82 (2022.01); G06V 20/70 (2022.01)
CPC G06T 7/001 (2013.01) [G06V 10/761 (2022.01); G06V 10/764 (2022.01); G06V 10/776 (2022.01); G06V 10/82 (2022.01); G06V 20/70 (2022.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30108 (2013.01); G06T 2207/30168 (2013.01)] 10 Claims
OG exemplary drawing
 
1. A method for determining quality of inspection data using a machine learning model of a vector neural network type including a plurality of vector neuron layers, the method comprising:
(a) generating a plurality of pieces of training data by classifying a plurality of pieces of data of a non-defective product into a plurality of classes and assigning a plurality of labels distinguishing the plurality of classes to the plurality of pieces of data of the non-defective product;
(b) executing learning of the machine learning model using the plurality of pieces of training data;
(c) preparing a known feature spectrum group obtained based on an output of at least one specific layer among the plurality of vector neuron layers when the plurality of pieces of training data are input to the learned machine learning model; and
(d) executing quality determination processing of the inspection data using the learned machine learning model and the known feature spectrum group, wherein
the (d) includes
(d1) calculating a feature spectrum based on the output of the specific layer in response to an input of the inspection data to the machine learning model,
(d2) calculating a similarity between the feature spectrum and the known feature spectrum group, and
(d3) determining the inspection data to be non-defective when the similarity is equal to or greater than a preset threshold value, and determining the inspection data to be defective when the similarity is less than the preset threshold value.